Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 6696
    Prev
    Next
    INDEX
    Explanations

    terms related to programming concepts, particularly those associated with structured data and UI components in Swift

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ypsies
    -0.58
    生平
    -0.54
    ecare
    -0.49
    μιουργ
    -0.48
    werth
    -0.46
    ungalow
    -0.45
    ीर
    -0.45
     Rossetti
    -0.45
    多人
    -0.44
     sns
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.76
    unknownFields
    0.72
    Autoritní
    0.71
     transférez
    0.70
     AssemblyCulture
    0.70
    Personensuche
    0.68
    RuleContext
    0.68
    OCCURRED
    0.65
    verwijspagina
    0.65
    PreferredItem
    0.65
    Activations Density 2.324%

    No Known Activations